Related papers: Critical Perspectives: A Benchmark Revealing Pitfa…

We present the first English corpus study on abusive language towards three conversational AI systems gathered "in the wild": an open-domain social bot, a rule-based chatbot, and a task-based system. To account for the complexity of the…

With the proliferation of online misinformation, fake news detection has gained importance in the artificial intelligence community. In this paper, we propose an adversarial benchmark that tests the ability of fake news detectors to reason…

The proliferation of social media platforms has led to an increase in the spread of hate speech, particularly targeting vulnerable communities. Unfortunately, existing methods for automatically identifying and blocking toxic language rely…

Toxic language is difficult to define, as it is not monolithic and has many variations in perceptions of toxicity. This challenge of detecting toxic language is increased by the highly contextual and subjectivity of its interpretation,…

Dialogue safety remains a pervasive challenge in open-domain human-machine interaction. Existing approaches propose distinctive dialogue safety taxonomies and datasets for detecting explicitly harmful responses. However, these taxonomies…

Detecting problematic content, such as hate speech, is a multifaceted and ever-changing task, influenced by social dynamics, user populations, diversity of sources, and evolving language. There has been significant efforts, both in academia…

Toxic comments in online platforms are an unavoidable social issue under the cloak of anonymity. Hate speech detection has been actively done for languages such as English, German, or Italian, where manually labeled corpus has been…

The concept of fairness is gaining popularity in academia and industry. Social media is especially vulnerable to media biases and toxic language and comments. We propose a fair ML pipeline that takes a text as input and determines whether…

Term weighting metrics assign weights to terms in order to discriminate the important terms from the less crucial ones. Due to this characteristic, these metrics have attracted growing attention in text classification and recently in…

Texts like news, encyclopedias, and some social media strive for objectivity. Yet bias in the form of inappropriate subjectivity - introducing attitudes via framing, presupposing truth, and casting doubt - remains ubiquitous. This kind of…

Hate speech detection on online social networks has become one of the emerging hot topics in recent years. With the broad spread and fast propagation speed across online social networks, hate speech makes significant impacts on society by…

Linguistic bias in online news and social media is widespread but difficult to measure. Yet, its identification and quantification remain difficult due to subjectivity, context dependence, and the scarcity of high-quality gold-label…

Stance detection has been widely studied as the task of determining if a social media post is positive, negative or neutral towards a specific issue, such as support towards vaccines. Research in stance detection has however often been…

Task oriented language understanding in dialog systems is often modeled using intents (task of a query) and slots (parameters for that task). Intent detection and slot tagging are, in turn, modeled using sentence classification and word…

Aspect-Based Sentiment Analysis (ABSA) provides a fine-grained understanding of opinions by linking sentiment to specific aspects in text. While transformer-based models excel at this task, their black-box nature limits their…

Online discourse is often perceived as polarized and unproductive. While some conversational discourse parsing frameworks are available, they do not naturally lend themselves to the analysis of contentious and polarizing discussions.…

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…

Automatic toxic language detection is critical for creating safe, inclusive online spaces. However, it is a highly subjective task, with perceptions of toxic language shaped by community norms and lived experience. Existing toxicity…

Text classifiers have promising applications in high-stake tasks such as resume screening and content moderation. These classifiers must be fair and avoid discriminatory decisions by being invariant to perturbations of sensitive attributes…

Text moderation for user generated content, which helps to promote healthy interaction among users, has been widely studied and many machine learning models have been proposed. In this work, we explore an alternative perspective by…